namenode | datanode | journaonode | zookeeper | nodemanager | resourcemanager | |
node1 | Y | Y | ||||
node2 | Y | Y | Y | Y | Y | |
node3 | Y | Y | Y | Y | Y | |
node4 | Y | Y | Y | Y |
1、core-site.xml
<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://mycluster</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>/var/hadoop/ha</value>
</property>
<property>
<name>hadoop.http.staticuser.user</name>
<value>/root</value>
</property>
<property>
<name>hadoop.proxyuser.root.hosts</name>
<value>*</value>
</property>
<property>
<name>hadoop.proxyuser.root.groups</name>
<value>*</value>
</property>
<property>
<name>ha.zookeeper.quorum</name>
<value>node2:2181,node3:2181,node4:2181</value>
</property>
</configuration>
2、hdfs-site.xml
<configuration>
<property>
<name>dfs.replication</name>
<value>2</value>
</property>
<property>
<name>dfs.nameservices</name>
<value>mycluster</value>
</property>
<property>
<name>dfs.ha.namenodes.mycluster</name>
<value>nn1,nn2</value>
</property>
<property>
<name>dfs.namenode.rpc-address.mycluster.nn1</name>
<value>node1:8020</value>
</property>
<property>
<name>dfs.namenode.rpc-address.mycluster.nn2</name>
<value>node2:8020</value>
</property>
<property>
<name>dfs.namenode.http-address.mycluster.nn1</name>
<value>node1:50070</value>
</property>
<property>
<name>dfs.namenode.http-address.mycluster.nn2</name>
<value>node2:50070</value>
</property>
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://node1:8485;node2:8485;node3:8485/mycluster</value>
</property>
<property>
<name>dfs.client.failover.proxy.provider.mycluster</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<property>
<name>dfs.ha.fencing.methods</name>
<value>sshfence</value>
</property>
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/root/.ssh/id_rsa</value>
</property>
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/var/hadoop/ha/journalnode</value>
</property>
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
</configuration>
3、mapred-site.xml
注意:mapreduce.application.classpath 换成自己的路径
输入 hadoop classpath,将:分割换成,分割
<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
<property>
<name>yarn.app.mapreduce.am.env</name>
<value>HADOOP_MAPRED_HOME=/usr/hadoop</value>
</property>
<property>
<name>mapreduce.map.env</name>
<value>HADOOP_MAPRED_HOME=/usr/hadoop</value>
</property>
<property>
<name>mapreduce.reduce.env</name>
<value>HADOOP_MAPRED_HOME=/usr/hadoop</value>
</property>
<property>
<name>mapreduce.application.classpath</name>
<value>
/usr/hadoop/etc/hadoop,
/usr/hadoop/share/hadoop/common/lib/*,
/usr/hadoop/share/hadoop/common/*,
/usr/hadoop/share/hadoop/hdfs,
/usr/hadoop/share/hadoop/hdfs/lib/*,
/usr/hadoop/share/hadoop/hdfs/*,
/usr/hadoop/share/hadoop/yarn/lib/*,
/usr/hadoop/share/hadoop/yarn/*,
/usr/hadoop/share/hadoop/mapreduce/lib/*,
/usr/hadoop/share/hadoop/mapreduce/*,
/usr/hadoop/contrib/capacity-scheduler/*.jar
</value>
</property>
4、yarn-site.xml
注意:mapreduce.application.classpath 换成自己的路径
输入 hadoop classpath,将:分割换成,分割
<configuration>
<property>
<name>yarn.resourcemanager.connect.retry-interval.ms</name> <value>2000</value>
</property>
<property>
<name>yarn.nodemanager.vmem-check-enabled</name>
<value>false</value>
</property>
<property>
<name>yarn.resourcemanager.ha.enabled</name>
<value>true</value>
</property>
<property>
<name>yarn.resourcemanager.ha.automatic-failover.enabled</name> <value>true</value>
</property>
<property>
<name>yarn.resourcemanager.ha.automatic-failover.embedded</name>
<value>true</value>
</property>
<property>
<name>yarn.resourcemanager.cluster-id</name>
<value>yarn-rm-cluster</value>
</property>
<property>
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm1</name>
<value>node3</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>node4</value>
</property>
<property>
<name>yarn.resourcemanager.recovery.enabled</name>
<value>true</value>
</property>
<property>
<name>yarn.resourcemanager.store.class</name>
<value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>
</property>
<property>
<name>yarn.resourcemanager.zk.state-store.address</name>
<value>node2:2181,node3:2181,node4:2181</value>
</property>
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>node2:2181,node3:2181,node4:2181</value>
</property>
<property>
<name>yarn.resourcemanager.address.rm1</name>
<value>node3:8132</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address.rm1</name>
<value>node3:8130</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address.rm1</name>
<value>node3:8088</value>
</property>
<property>
<name>yarn.resourcemanager.address.rm2</name>
<value>node4:8132</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address.rm2</name>
<value>node4:8130</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address.rm2</name>
<value>node4:8088</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.nodemanager.aux-services.mapreduce_shuffle.class</name>
<value>org.apache.hadoop.mapred.ShuffleHandler</value>
</property>
<property>
<name>yarn.application.classpath</name>
<value>
/usr/hadoop/etc/hadoop,
/usr/hadoop/share/hadoop/common/*,
/usr/hadoop/share/hadoop/hdfs,
/usr/hadoop/share/hadoop/hdfs/lib/*,
/usr/hadoop/share/hadoop/hdfs/*,
/usr/hadoop/share/hadoop/mapreduce/lib/*,
/usr/hadoop/share/hadoop/common/lib/*,
/usr/hadoop/share/hadoop/mapreduce/*,
/usr/hadoop/share/hadoop/yarn,
/usr/hadoop/share/hadoop/yarn/lib/*,
/usr/hadoop/share/hadoop/yarn/*
</value>
</property>
</configuration>
5、hadoop-env.sh
将JAVA_HOME换成自己的目录
export JAVA_HOME=/usr/java/jdk1.8.0_91
export HDFS_NAMENODE_USER=root
export HDFS_DATANODE_USER=root
export HDFS_ZKFC_USER=root
export HDFS_JOURNALNODE_USER=root
export YARN_NODEMANAGER_USER=root
export YARN_RESOURCEMANAGER_USER=root
6.slaves
node2
node3
node4
7、首次启动命令
node1,node2,node3:journalnode hadoop-daemon.sh start journalnode
node1:hdfs namenode -format
node1:hadoop-daemon.sh start namenode
node2:hdfs namenode -bootstrapStandby
node1:hdfs zkfc -formatZK
yarn
node1:start-yarn.sh
node3 node4:yarn-daemon.sh start resourcemanager
8、以后启动命令
启动hdfs:node1:start-dfs.sh
启动yarn:node1:start-yarn.sh
node3: yarn-daemon.sh start resourcemanager